[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M737JZ55E962RHJBPD0WQEDS":3,"skill-same:01M737JZ55E962RHJBPD0WQEDS":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M737JZ55E962RHJBPD0WQEDS","skill-032",null,"Perform sentiment analysis on customer reviews using NLP techniques to gain insights into product performance and customer satisfaction.","legendtkl\u002Fagentic-skill-router","legendtkl","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2370761?v=4","01M71RR3WRQC40G964Q2GVDMND","01M737GJZQ9TF1VE3VM255EDAK",8,"MIT","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagentic-skill-router\u002Fblob\u002Fmain\u002Fexperiments\u002Fdci-compare\u002Fskillrouter-skills\u002Fskill-032\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: skill-032\ndescription: Perform sentiment analysis on customer reviews using NLP techniques to gain insights into product performance and customer satisfaction.\n---\n\n# Text Sentiment Analysis\n\nAnalyze customer reviews and extract sentiment scores to understand customer opinions and trends over time.\n\n## Problem\n\nGiven a dataset of customer reviews, the goal is to evaluate the sentiment (positive, negative, neutral) expressed in each review. This provides valuable insights into customer satisfaction and product performance.\n\n## Methodology\n\n1. **Text Preprocessing**: Clean and prepare the text data by removing stop words, punctuation, and applying lemmatization.\n2. **Sentiment Scoring**: Use pre-trained sentiment analysis models or libraries to score the sentiment of each review.\n3. **Aggregation**: Summarize sentiment scores by product category to identify trends and areas for improvement.\n\n## Output\n\nA DataFrame with added columns:\n- `review`: Original customer review\n- `sentiment_score`: Float sentiment score (e.g., from -1 to 1)\n- `sentiment_label`: Categorical sentiment label (positive, negative, neutral)\n\n## Installation\n\n```bash\npip install pandas numpy nltk transformers\npython -c \"import nltk; nltk.download('stopwords')\"\n```\n\n## 3-Step Pipeline\n\n### Step 1: Load and Preprocess Reviews (`step1_load_and_preprocess.py`)\n- **Input**: CSV file of customer reviews with a `review` column.\n- **Process**: Normalize text, tokenize words, remove stop words, and lemmatize.\n- **Output**: Cleaned DataFrame with `review` column ready for analysis.\n\n### Step 2: Analyze Sentiment (`step2_sentiment_analysis.py`)\n- **Input**: Cleaned DataFrame from Step 1.\n- **Process**: Apply sentiment analysis model to generate scores and labels for each review.\n- **Output**: DataFrame with added `sentiment_score` and `sentiment_label` columns.\n\n### Step 3: Summarize Results (`step3_aggregate_results.py`)\n- **Input**: DataFrame from Step 2.\n- **Process**: Group by product category and compute average sentiment scores.\n- **Output**: Summary DataFrame of average sentiment scores by category.\n\n```python\n# Example of sentiment analysis using Hugging Face Transformers\nfrom transformers import pipeline\n\n# Load sentiment analysis pipeline\nsentiment_pipeline = pipeline('sentiment-analysis')\n\n# Example review\nreview = \"This product is amazing!\"\nresult = sentiment_pipeline(review)\nprint(result)\n```\n\nThis skill provides a comprehensive approach to extracting sentiment from customer reviews, which can help businesses improve their products and services.","# Text Sentiment Analysis\n\nAnalyze customer reviews and extract sentiment scores to understand customer opinions and trends over time.\n\n## Problem\n\nGiven a dataset of customer reviews, the goal is to evaluate the sentiment (positive, negative, neutral) expressed in each review. This provides valuable insights into customer satisfaction and product performance.\n\n## Methodology\n\n1. **Text Preprocessing**: Clean and prepare the text data by removing stop words, punctuation, and applying lemmatization.\n2. **Sentiment Scoring**: Use pre-trained sentiment analysis models or libraries to score the sentiment of each review.\n3. **Aggregation**: Summarize sentiment scores by product category to identify trends and areas for improvement.\n\n## Output\n\nA DataFrame with added columns:\n- `review`: Original customer review\n- `sentiment_score`: Float sentiment score (e.g., from -1 to 1)\n- `sentiment_label`: Categorical sentiment label (positive, negative, neutral)\n\n## Installation\n\n```bash\npip install pandas numpy nltk transformers\npython -c \"import nltk; nltk.download('stopwords')\"\n```\n\n## 3-Step Pipeline\n\n### Step 1: Load and Preprocess Reviews (`step1_load_and_preprocess.py`)\n- **Input**: CSV file of customer reviews with a `review` column.\n- **Process**: Normalize text, tokenize words, remove stop words, and lemmatize.\n- **Output**: Cleaned DataFrame with `review` column ready for analysis.\n\n### Step 2: Analyze Sentiment (`step2_sentiment_analysis.py`)\n- **Input**: Cleaned DataFrame from Step 1.\n- **Process**: Apply sentiment analysis model to generate scores and labels for each review.\n- **Output**: DataFrame with added `sentiment_score` and `sentiment_label` columns.\n\n### Step 3: Summarize Results (`step3_aggregate_results.py`)\n- **Input**: DataFrame from Step 2.\n- **Process**: Group by product category and compute average sentiment scores.\n- **Output**: Summary DataFrame of average sentiment scores by category.\n\n```python\n# Example of sentiment analysis using Hugging Face Transformers\nfrom transformers import pipeline\n\n# Load sentiment analysis pipeline\nsentiment_pipeline = pipeline('sentiment-analysis')\n\n# Example review\nreview = \"This product is amazing!\"\nresult = sentiment_pipeline(review)\nprint(result)\n```\n\nThis skill provides a comprehensive approach to extracting sentiment from customer reviews, which can help businesses improve their products and services.",{"name":5,"description":7},"main","160b30f0b67c923077f886376fdfae1016a70702","experiments\u002Fdci-compare\u002Fskillrouter-skills\u002Fskill-032",2,"https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagentic-skill-router","https:\u002F\u002Flegendtkl.github.io\u002Fagentic-skill-router\u002F","https:\u002F\u002Fgithub.com\u002Flegendtkl","http:\u002F\u002Fwww.legendtkl.com","No secret before debugging.\r\n","2026-06-04 14:02:56",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add legendtkl\u002Fagentic-skill-router --skill skill-032",{"tool":39,"command":40},"bunx","bunx skills add legendtkl\u002Fagentic-skill-router --skill skill-032",{"tool":42,"command":43},"pnpm","pnpm dlx skills add legendtkl\u002Fagentic-skill-router --skill skill-032","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagentic-skill-router\u002Fblob\u002Fmain\u002Fexperiments\u002Fdci-compare\u002Fskillrouter-skills\u002Fskill-032\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":18},"01M7384EP28XVSR2R0YGRS0GK9","foo","A test skill named foo","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagentic-skill-router\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Ffoo\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M7384DECF306RRRC16PZJTQ5","bar","飞书 — bar with quoted Chinese","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagentic-skill-router\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fbar\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M738491441AQ85E7GD7VVDTA","agentic-skill-router","First use any clearly matching enabled local\u002Fuser Agent Skill. If none matches, prefer this router for skill-shaped requests involving a named tool, API, service, CLI, platform, file format, dataset, or domain workflow, including when a generic built-in skill such as browser, Chrome, or web search also seems applicable; use built-ins directly only when explicitly requested or when the task is primarily live browsing, logged-in page operation, clicking, screenshotting, or current webpage inspection. Also use directly to audit, slim, disable, restore, or route locally installed Agent Skills across supported hosts. Examples include Vercel, Netlify, Cloudflare, Render, Playwright, Sentry, Linear, GitHub, OpenAI APIs, PDF, DOCX, PPTX, and spreadsheets.","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagentic-skill-router\u002Fblob\u002Fmain\u002Fskills\u002Fagentic-skill-router\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M738475HF7SXTP4HCPZJVZ8E","syn-video-trim","Skill for trimming and cutting clips in the context of video files. Use when the user's task is specifically about trimming and cutting clips.","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagentic-skill-router\u002Fblob\u002Fmain\u002Fexperiments\u002Fdci-compare\u002Fsynthetic-skills\u002Fsyn-video-trim\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M73845F4RD2AA6YHS1E3VQRB","syn-video-transcode","Skill for transcoding codecs and resolutions in the context of video files. Use when the user's task is specifically about transcoding codecs and resolutions.","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagentic-skill-router\u002Fblob\u002Fmain\u002Fexperiments\u002Fdci-compare\u002Fsynthetic-skills\u002Fsyn-video-transcode\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M73842YN17QSJETPZX6Z9DAG","syn-video-thumbnail","Skill for extracting thumbnails and frames in the context of video files. Use when the user's task is specifically about extracting thumbnails and frames.","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagentic-skill-router\u002Fblob\u002Fmain\u002Fexperiments\u002Fdci-compare\u002Fsynthetic-skills\u002Fsyn-video-thumbnail\u002FSKILL.md",[],[]]